A Framework for Understanding the Role of Morphology in Universal Dependency Parsing - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

A Framework for Understanding the Role of Morphology in Universal Dependency Parsing

Abstract

This paper presents a simple framework for characterizing morphological complexity and how it encodes syntactic information. In particular, we propose a new measure of morphosyntactic complexity in terms of governordependent preferential attachment that explains parsing performance. Through experiments on dependency parsing with data from Universal Dependencies (UD), we show that representations derived from morphological attributes deliver important parsing performance improvements over standard word form embeddings when trained on the same datasets. We also show that the new morphosyntactic complexity measure is predictive of the gains provided by using morphological attributes over plain forms on parsing scores, making it a tool to distinguish languages using morphology as a syntactic marker from others.
Fichier principal
Vignette du fichier
doc.pdf (167.96 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-01943934 , version 1 (04-12-2018)

Identifiers

  • HAL Id : hal-01943934 , version 1

Cite

Mathieu Dehouck, Pascal Denis. A Framework for Understanding the Role of Morphology in Universal Dependency Parsing. EMNLP 2018 - Conference on Empirical Methods in Natural Language Processing, Oct 2018, Brussels, Belgium. ⟨hal-01943934⟩
125 View
255 Download

Share

Gmail Mastodon Facebook X LinkedIn More